Key result
Natural language processing accurately extracts ETT results to yield a 0.81 C-statistic for risk discrimination.
Why the study?
Is natural language processing an accurate and efficient strategy to extract Exercise Treadmill Test results for large-scale outcome studies?
Observational
Is natural language processing an accurate and efficient strategy to extract Exercise Treadmill Test results for large-scale outcome studies?
Effect estimate: C-statistic 0.81 (95% CI 0.7-0.92)
p-value: p=<0.001
Natural language processing is an accurate and efficient strategy for extracting exercise treadmill test results to facilitate large-scale outcome studies.
NLP may facilitate large-scale ETT analyses from EHRs; leaves open need for prospective validation before clinical adoption.
<0.001) by categories for normal (0.08%), ischemic (1.9%), nondiagnostic (0.77%), and equivocal (0.58%) groups achieving good discrimination (C-statistic, 0.81; 95% CI, 0.7-0.92). Conclusions Natural language processing is an accurate and efficient strategy to facilitate large-scale outcome studies of noninvasive cardiac tests. We found that most patients are at low risk and have normal ETT results, while those with abnormal, nondiagnostic, or equivocal results have slightly higher risks and warrant future investigation.
No takes yet. Share an insight, caveat, or question.
Zheng et al. (2020) conducted an observational in Exercise Treadmill Test (ETT) evaluation. Natural language processing (NLP) was evaluated on Risk discrimination by ETT result categories (C-statistic 0.81, 95% CI 0.7-0.92, p=<0.001). Natural language processing accurately identified and extracted exercise treadmill test results, achieving good risk discrimination (C-statistic 0.81; 95% CI 0.7-0.92).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: